Research on rotor condition monitoring based on D-S evidence theory

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Aiming at the problem of continuous monitoring of rotating machinery, a new method based on D-S evidence theory is proposed for rotor condition monitoring. The discriminant vectors can be constructed by calculating the time domain parameters and frequency domain parameters from online monitoring data. Then the Euclidean distance between the discriminant vector and the standard vectors is calculated to acquire the probability of each rotor operating state. The multi-channel information is integrated to acquire the results of time domain and frequency domain by D-S evidence theory. Finally the final recognition result is obtained by fusing the time domain and frequency domain results. Experimental results show that the proposed method can improve the accuracy of rotor state identification and it has a good ability to distinguish the typical rotor operating states.

Original languageEnglish
Title of host publication2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages848-853
Number of pages6
ISBN (Electronic)9781509008216
DOIs
StatePublished - 21 Oct 2016
Event13th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2016 - Xian, China
Duration: 19 Aug 201622 Aug 2016

Publication series

Name2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2016

Conference

Conference13th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2016
Country/TerritoryChina
CityXian
Period19/08/1622/08/16

Keywords

  • Condition monitoring
  • D-S evidence theory
  • Frequency domain parameters
  • Rotor
  • Time domain parameters

Fingerprint

Dive into the research topics of 'Research on rotor condition monitoring based on D-S evidence theory'. Together they form a unique fingerprint.

Cite this